Combining Multiple Resources, Evidences and Criteria for Genomic Information Retrieval

We participated in the passage retrieval and aspect retrieval subtasks of the TREC 2006 Genomics Track. This paper describes the methods developed for these two subtasks. For passage retrieval, our query expansion method utilizes multiple external biomedical resources to extract acronyms, aliases, and synonyms, and we propose a post-processing step which combines the evidence from multiple scoring methods to improve relevance-based passage rankings. For aspect retrieval, our method estimates the topical aspects of the retrieved passages and generates passage rankings by considering both topical relevance and topical novelty. Empirical results demonstrate the effectiveness of these methods.